x86-64: correct / adjust prefix emission

First and foremost REX must come last. Next JumpInterSegment branches
can't possibly have a REX prefix, as they're consistently CpuNo64. And
finally make BND prefix handling in output_branch() consistent with that
of other prefixes in the same function, and make its placement among
prefixes consistent with output_jump() (which, oddly enough, still isn't
the supposedly canonical order specified by the *_PREFIX definitions).

10 files changed, 72 insertions, 63 deletions

diff --git a/gas/ChangeLog b/gas/ChangeLog
index 578d76f..286f018 100644
--- a/gas/ChangeLog
+++ b/gas/ChangeLog
@@ -1,5 +1,21 @@
 2019-12-27  Jan Beulich  <jbeulich@suse.com>
 
+	* config/tc-i386.c (output_branch): Handle BND prefix the same
+	way as other prefixes. Emit it last before REX.
+	(output_jump): Emit BND before REX.
+	(output_interseg_jump): Don't emit REX.
+	* testsuite/gas/i386/x86-64-branch-2.s,
+	testsuite/gas/i386/x86-64-branch-3.s,
+	testsuite/gas/i386/x86-64-mpx-branch-1.s,
+	testsuite/gas/i386/x86-64-mpx-branch-2.s: Add REX.W cases.
+	* testsuite/gas/i386/x86-64-mpx-branch-2.d: Match output against
+	x86-64-mpx-branch-1.d.
+	* testsuite/gas/i386/x86-64-branch-2.d,
+	testsuite/gas/i386/x86-64-branch-3.d,
+	testsuite/gas/i386/x86-64-mpx-branch-1.d: Adjust expectations.
+
+2019-12-27  Jan Beulich  <jbeulich@suse.com>
+
 	* config/tc-i386.c (flip_code16): New.
 	(output_branch, output_jump): Use it.
 	(i386_displacement): Restrict template set to just direct
diff --git a/gas/config/tc-i386.c b/gas/config/tc-i386.c
index 770fa52..8e89b00 100644
--- a/gas/config/tc-i386.c
+++ b/gas/config/tc-i386.c
@@ -7910,8 +7910,8 @@ output_branch (void)
   /* BND prefixed jump.  */
   if (i.prefix[BND_PREFIX] != 0)
     {
-      FRAG_APPEND_1_CHAR (i.prefix[BND_PREFIX]);
-      i.prefixes -= 1;
+      prefix++;
+      i.prefixes--;
     }
 
   if (i.prefixes != 0 && !intel_syntax)
@@ -7930,6 +7930,8 @@ output_branch (void)
   if (i.prefix[SEG_PREFIX] == CS_PREFIX_OPCODE
       || i.prefix[SEG_PREFIX] == DS_PREFIX_OPCODE)
     *p++ = i.prefix[SEG_PREFIX];
+  if (i.prefix[BND_PREFIX] != 0)
+    *p++ = BND_PREFIX_OPCODE;
   if (i.prefix[REX_PREFIX] != 0)
     *p++ = i.prefix[REX_PREFIX];
   *p = i.tm.base_opcode;
@@ -8042,16 +8044,16 @@ output_jump (void)
 	size = 2;
     }
 
-  if (i.prefix[REX_PREFIX] != 0)
+  /* BND prefixed jump.  */
+  if (i.prefix[BND_PREFIX] != 0)
     {
-      FRAG_APPEND_1_CHAR (i.prefix[REX_PREFIX]);
+      FRAG_APPEND_1_CHAR (i.prefix[BND_PREFIX]);
       i.prefixes -= 1;
     }
 
-  /* BND prefixed jump.  */
-  if (i.prefix[BND_PREFIX] != 0)
+  if (i.prefix[REX_PREFIX] != 0)
     {
-      FRAG_APPEND_1_CHAR (i.prefix[BND_PREFIX]);
+      FRAG_APPEND_1_CHAR (i.prefix[REX_PREFIX]);
       i.prefixes -= 1;
     }
 
@@ -8109,11 +8111,8 @@ output_interseg_jump (void)
       i.prefixes -= 1;
       code16 ^= CODE16;
     }
-  if (i.prefix[REX_PREFIX] != 0)
-    {
-      prefix++;
-      i.prefixes -= 1;
-    }
+
+  gas_assert (!i.prefix[REX_PREFIX]);
 
   size = 4;
   if (code16)
diff --git a/gas/testsuite/gas/i386/x86-64-branch-2.d b/gas/testsuite/gas/i386/x86-64-branch-2.d
index 5078daa..196fa8e 100644
--- a/gas/testsuite/gas/i386/x86-64-branch-2.d
+++ b/gas/testsuite/gas/i386/x86-64-branch-2.d
@@ -6,10 +6,12 @@
 
 Disassembly of section .text:
 
-0+ <bar-0x4>:
-[ 	]*[a-f0-9]+:	66 e9 00 00          	jmpw   4 <bar>	2: R_X86_64_PC16	foo-0x2
+0+ <bar-0xb>:
+[ 	]*[a-f0-9]+:	66 e9 00 00          	jmpw   4 <bar-0x7>	2: R_X86_64_PC16	foo-0x2
+[ 	]*[a-f0-9]+:	66 48 e9 00 00 00 00 	data16 jmpq b <bar>	7: R_X86_64_PLT32	foo-0x4
 
-0+4 <bar>:
+0+b <bar>:
 [ 	]*[a-f0-9]+:	89 c3                	mov    %eax,%ebx
-[ 	]*[a-f0-9]+:	66 e8 00 00          	callw  a <bar\+0x6>	8: R_X86_64_PC16	foo-0x2
+[ 	]*[a-f0-9]+:	66 e8 00 00          	callw  11 <bar\+0x6>	f: R_X86_64_PC16	foo-0x2
+[ 	]*[a-f0-9]+:	66 48 e8 00 00 00 00 	data16 callq 18 <bar\+0xd>	14: R_X86_64_PLT32	foo-0x4
 #pass
diff --git a/gas/testsuite/gas/i386/x86-64-branch-2.s b/gas/testsuite/gas/i386/x86-64-branch-2.s
index 16c85a3..3a4911b 100644
--- a/gas/testsuite/gas/i386/x86-64-branch-2.s
+++ b/gas/testsuite/gas/i386/x86-64-branch-2.s
@@ -1,7 +1,9 @@
 	.text
 	data16 jmp foo
+	data16 rex.w jmp foo
 
 bar:
 	mov %eax, %ebx
 
 	data16 call foo
+	data16 rex.w call foo
diff --git a/gas/testsuite/gas/i386/x86-64-branch-3.d b/gas/testsuite/gas/i386/x86-64-branch-3.d
index c66647c..7b9e21d 100644
--- a/gas/testsuite/gas/i386/x86-64-branch-3.d
+++ b/gas/testsuite/gas/i386/x86-64-branch-3.d
@@ -6,11 +6,14 @@
 
 Disassembly of section .text:
 
-0+ <bar-0x6>:
-[ 	]*[a-f0-9]+:	66 e9 00 00 00 00    	data16 jmpq 6 <bar>	2: R_X86_64_PLT32	foo-0x4
+0+ <bar-0xd>:
+[ 	]*[a-f0-9]+:	66 e9 00 00 00 00    	data16 jmpq 6 <bar-0x7>	2: R_X86_64_PLT32	foo-0x4
+[ 	]*[a-f0-9]+:	66 48 e9 00 00 00 00 	data16 rex\.W jmpq d <bar>	9: R_X86_64_PLT32	foo-0x4
 
-0+6 <bar>:
+0+d <bar>:
 [ 	]*[a-f0-9]+:	89 c3                	mov    %eax,%ebx
-[ 	]*[a-f0-9]+:	66 e8 00 00 00 00    	data16 callq e <bar\+0x8>	a: R_X86_64_PLT32	foo-0x4
-[ 	]*[a-f0-9]+:	66 c7 f8 00 00       	xbeginw 13 <bar\+0xd>	11: R_X86_64_PC16	foo-0x2
+[ 	]*[a-f0-9]+:	66 e8 00 00 00 00    	data16 callq 15 <bar\+0x8>	11: R_X86_64_PLT32	foo-0x4
+[ 	]*[a-f0-9]+:	66 48 e8 00 00 00 00 	data16 rex\.W callq 1c <bar\+0xf>	18: R_X86_64_PLT32	foo-0x4
+[ 	]*[a-f0-9]+:	66 c7 f8 00 00       	xbeginw 21 <bar\+0x14>	1f: R_X86_64_PC16	foo-0x2
+[ 	]*[a-f0-9]+:	66 48 c7 f8 00 00 00 00 	data16 xbeginq 29 <bar\+0x1c>	25: R_X86_64_PLT32	foo-0x4
 #pass
diff --git a/gas/testsuite/gas/i386/x86-64-branch-3.s b/gas/testsuite/gas/i386/x86-64-branch-3.s
index 42bdac0..cc16487 100644
--- a/gas/testsuite/gas/i386/x86-64-branch-3.s
+++ b/gas/testsuite/gas/i386/x86-64-branch-3.s
@@ -1,9 +1,12 @@
 	.text
 	data16 jmp foo
+	data16 rex.w jmp foo
 
 bar:
 	mov %eax, %ebx
 
 	data16 call foo
+	data16 rex.w call foo
 
 	data16 xbegin foo
+	data16 rex.w xbegin foo
diff --git a/gas/testsuite/gas/i386/x86-64-mpx-branch-1.d b/gas/testsuite/gas/i386/x86-64-mpx-branch-1.d
index 7ee6c6b..03e9675 100644
--- a/gas/testsuite/gas/i386/x86-64-mpx-branch-1.d
+++ b/gas/testsuite/gas/i386/x86-64-mpx-branch-1.d
@@ -8,22 +8,24 @@
 
 Disassembly of section .text:
 
-0+ <foo1-0xc>:
-[ 	]*[a-f0-9]+:	f2 e8 00 00 00 00    	bnd callq 6 <foo1-0x6>	2: R_X86_64_PC32	\*ABS\*\+0x10003c
-[ 	]*[a-f0-9]+:	f2 e9 00 00 00 00    	bnd jmpq c <foo1>	8: R_X86_64_PC32	\*ABS\*\+0x10003c
+0+ <foo1-0x1c>:
+[ 	]*[a-f0-9]+:	f2 e8 00 00 00 00    	bnd callq 6 <foo1-0x16>	2: R_X86_64_PC32	\*ABS\*\+0x10003c
+[ 	]*[a-f0-9]+:	f2 e9 00 00 00 00    	bnd jmpq c <foo1-0x10>	8: R_X86_64_PC32	\*ABS\*\+0x10003c
+[ 	]*[a-f0-9]+:	66 f2 48 e8 00 00 00 00 	data16 bnd callq 14 <foo1-0x8>	10: R_X86_64_PC32	\*ABS\*\+0x10003c
+[ 	]*[a-f0-9]+:	66 f2 48 e9 00 00 00 00 	data16 bnd jmpq 1c <foo1>	18: R_X86_64_PC32	\*ABS\*\+0x10003c
 
-0+c <foo1>:
-[ 	]*[a-f0-9]+:	f2 eb fd             	bnd jmp c <foo1>
-[ 	]*[a-f0-9]+:	f2 72 fa             	bnd jb c <foo1>
-[ 	]*[a-f0-9]+:	f2 e8 f4 ff ff ff    	bnd callq c <foo1>
-[ 	]*[a-f0-9]+:	f2 eb 09             	bnd jmp 24 <foo2>
-[ 	]*[a-f0-9]+:	f2 72 06             	bnd jb 24 <foo2>
-[ 	]*[a-f0-9]+:	f2 e8 00 00 00 00    	bnd callq 24 <foo2>
+0+1c <foo1>:
+[ 	]*[a-f0-9]+:	f2 eb fd             	bnd jmp 1c <foo1>
+[ 	]*[a-f0-9]+:	f2 72 fa             	bnd jb 1c <foo1>
+[ 	]*[a-f0-9]+:	f2 e8 f4 ff ff ff    	bnd callq 1c <foo1>
+[ 	]*[a-f0-9]+:	f2 eb 09             	bnd jmp 34 <foo2>
+[ 	]*[a-f0-9]+:	f2 72 06             	bnd jb 34 <foo2>
+[ 	]*[a-f0-9]+:	f2 e8 00 00 00 00    	bnd callq 34 <foo2>
 
-0+24 <foo2>:
-[ 	]*[a-f0-9]+:	f2 e9 00 00 00 00    	bnd jmpq 2a <foo2\+0x6>	26: R_X86_64_PLT32	foo-0x4
-[ 	]*[a-f0-9]+:	f2 0f 82 00 00 00 00 	bnd jb 31 <foo2\+0xd>	2d: R_X86_64_PLT32	foo-0x4
-[ 	]*[a-f0-9]+:	f2 e8 00 00 00 00    	bnd callq 37 <foo2\+0x13>	33: R_X86_64_PLT32	foo-0x4
-[ 	]*[a-f0-9]+:	f2 e9 00 00 00 00    	bnd jmpq 3d <foo2\+0x19>	39: R_X86_64_PLT32	foo-0x4
-[ 	]*[a-f0-9]+:	f2 0f 82 00 00 00 00 	bnd jb 44 <foo2\+0x20>	40: R_X86_64_PLT32	foo-0x4
-[ 	]*[a-f0-9]+:	f2 e8 00 00 00 00    	bnd callq 4a <foo2\+0x26>	46: R_X86_64_PLT32	foo-0x4
+0+34 <foo2>:
+[ 	]*[a-f0-9]+:	f2 e9 00 00 00 00    	bnd jmpq 3a <foo2\+0x6>	36: R_X86_64_PLT32	foo-0x4
+[ 	]*[a-f0-9]+:	f2 0f 82 00 00 00 00 	bnd jb 41 <foo2\+0xd>	3d: R_X86_64_PLT32	foo-0x4
+[ 	]*[a-f0-9]+:	f2 e8 00 00 00 00    	bnd callq 47 <foo2\+0x13>	43: R_X86_64_PLT32	foo-0x4
+[ 	]*[a-f0-9]+:	f2 e9 00 00 00 00    	bnd jmpq 4d <foo2\+0x19>	49: R_X86_64_PLT32	foo-0x4
+[ 	]*[a-f0-9]+:	f2 0f 82 00 00 00 00 	bnd jb 54 <foo2\+0x20>	50: R_X86_64_PLT32	foo-0x4
+[ 	]*[a-f0-9]+:	f2 e8 00 00 00 00    	bnd callq 5a <foo2\+0x26>	56: R_X86_64_PLT32	foo-0x4
diff --git a/gas/testsuite/gas/i386/x86-64-mpx-branch-1.s b/gas/testsuite/gas/i386/x86-64-mpx-branch-1.s
index 3cdb109..16cd019 100644
--- a/gas/testsuite/gas/i386/x86-64-mpx-branch-1.s
+++ b/gas/testsuite/gas/i386/x86-64-mpx-branch-1.s
@@ -2,6 +2,9 @@
 	bnd call	0x100040
 	bnd jmp		0x100040
 
+	bnd data16 rex.w call	0x100040
+	bnd data16 rex.w jmp	0x100040
+
 foo1:
 	bnd jmp		foo1
 	bnd jb		foo1
diff --git a/gas/testsuite/gas/i386/x86-64-mpx-branch-2.d b/gas/testsuite/gas/i386/x86-64-mpx-branch-2.d
index 96e0009..c61b3af 100644
--- a/gas/testsuite/gas/i386/x86-64-mpx-branch-2.d
+++ b/gas/testsuite/gas/i386/x86-64-mpx-branch-2.d
@@ -1,29 +1,5 @@
 #as: -J -madd-bnd-prefix
 #objdump: -dwr
 #name: x86-64 branch with BND prefix
+#dump: x86-64-mpx-branch-1.d
 #notarget: *-*-solaris*
-
-.*: +file format .*
-
-
-Disassembly of section .text:
-
-0+ <foo1-0xc>:
-[ 	]*[a-f0-9]+:	f2 e8 00 00 00 00    	bnd callq 6 <foo1-0x6>	2: R_X86_64_PC32	\*ABS\*\+0x10003c
-[ 	]*[a-f0-9]+:	f2 e9 00 00 00 00    	bnd jmpq c <foo1>	8: R_X86_64_PC32	\*ABS\*\+0x10003c
-
-0+c <foo1>:
-[ 	]*[a-f0-9]+:	f2 eb fd             	bnd jmp c <foo1>
-[ 	]*[a-f0-9]+:	f2 72 fa             	bnd jb c <foo1>
-[ 	]*[a-f0-9]+:	f2 e8 f4 ff ff ff    	bnd callq c <foo1>
-[ 	]*[a-f0-9]+:	f2 eb 09             	bnd jmp 24 <foo2>
-[ 	]*[a-f0-9]+:	f2 72 06             	bnd jb 24 <foo2>
-[ 	]*[a-f0-9]+:	f2 e8 00 00 00 00    	bnd callq 24 <foo2>
-
-0+24 <foo2>:
-[ 	]*[a-f0-9]+:	f2 e9 00 00 00 00    	bnd jmpq 2a <foo2\+0x6>	26: R_X86_64_PLT32	foo-0x4
-[ 	]*[a-f0-9]+:	f2 0f 82 00 00 00 00 	bnd jb 31 <foo2\+0xd>	2d: R_X86_64_PLT32	foo-0x4
-[ 	]*[a-f0-9]+:	f2 e8 00 00 00 00    	bnd callq 37 <foo2\+0x13>	33: R_X86_64_PLT32	foo-0x4
-[ 	]*[a-f0-9]+:	f2 e9 00 00 00 00    	bnd jmpq 3d <foo2\+0x19>	39: R_X86_64_PLT32	foo-0x4
-[ 	]*[a-f0-9]+:	f2 0f 82 00 00 00 00 	bnd jb 44 <foo2\+0x20>	40: R_X86_64_PLT32	foo-0x4
-[ 	]*[a-f0-9]+:	f2 e8 00 00 00 00    	bnd callq 4a <foo2\+0x26>	46: R_X86_64_PLT32	foo-0x4
diff --git a/gas/testsuite/gas/i386/x86-64-mpx-branch-2.s b/gas/testsuite/gas/i386/x86-64-mpx-branch-2.s
index 5fe9088..15c53b0 100644
--- a/gas/testsuite/gas/i386/x86-64-mpx-branch-2.s
+++ b/gas/testsuite/gas/i386/x86-64-mpx-branch-2.s
@@ -2,6 +2,9 @@
 	call	0x100040
 	jmp	0x100040
 
+	data16 rex.w call	0x100040
+	data16 rex.w jmp	0x100040
+
 foo1:
 	jmp	foo1
 	jb	foo1